FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control
Ye, Yutong, Zhou, Yingbo, Liu, Zhusen, Du, Xiao, Zhou, Hao, Lian, Xiang, Chen, Mingsong
–arXiv.org Artificial Intelligence
Although Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods have been extensively studied, their practical applications still raise some serious issues such as high learning cost and poor generalizability. This is because the ``trial-and-error'' training style makes RL agents extremely dependent on the specific traffic environment, which also requires a long convergence time. To address these issues, we propose a novel Federated Imitation Learning (FIL)-based framework for multi-intersection TSC, named FitLight, which allows RL agents to plug-and-play for any traffic environment without additional pre-training cost. Unlike existing imitation learning approaches that rely on pre-training RL agents with demonstrations, FitLight allows real-time imitation learning and seamless transition to reinforcement learning. Due to our proposed knowledge-sharing mechanism and novel hybrid pressure-based agent design, RL agents can quickly find a best control policy with only a few episodes. Moreover, for resource-constrained TSC scenarios, FitLight supports model pruning and heterogeneous model aggregation, such that RL agents can work on a micro-controller with merely 16{\it KB} RAM and 32{\it KB} ROM. Extensive experiments demonstrate that, compared to state-of-the-art methods, FitLight not only provides a superior starting point but also converges to a better final solution on both real-world and synthetic datasets, even under extreme resource limitations.
arXiv.org Artificial Intelligence
Feb-17-2025
- Country:
- Asia (0.48)
- North America > United States (0.68)
- Genre:
- Research Report > Promising Solution (0.48)
- Industry:
- Transportation
- Ground > Road (1.00)
- Infrastructure & Services (1.00)
- Transportation
- Technology: